library(readr)
readr::fwf_empty("aaup2.txt")[1:2]
## $begin
## [1] 0 6 40 45 49 53 57 61 66 70 74 79 83 87 92 95
##
## $end
## [1] 5 39 43 48 52 56 60 65 69 73 78 82 86 90 94 NA
aaup2 <- read_fwf("aaup2.txt",
fwf_cols(V1 = 6, V2 = 31, V3 = 3,
V4 = 4, V5 = 4,
V6 = 4, V7 = 4,
V8 = 4, V9 = 5,
V10 = 4, V11 = 4,
V12 = 5, V13 = 4,
V14 = 4, V15 = 4,
V16 = 4, V17 = 5))
## Parsed with column specification:
## cols(
## V1 = col_double(),
## V2 = col_character(),
## V3 = col_character(),
## V4 = col_character(),
## V5 = col_character(),
## V6 = col_character(),
## V7 = col_character(),
## V8 = col_double(),
## V9 = col_character(),
## V10 = col_character(),
## V11 = col_character(),
## V12 = col_double(),
## V13 = col_double(),
## V14 = col_double(),
## V15 = col_double(),
## V16 = col_double(),
## V17 = col_double()
## )
aaup2[aaup2 == "*"] <- NA
head(aaup2)
## # A tibble: 6 x 17
## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <chr> <chr> <chr> <dbl> <dbl>
## 1 1061 Alask~ AK IIB 454 382 362 382 567 485 471 487 6
## 2 1063 Univ.~ AK I 686 560 432 508 914 753 572 677 74
## 3 1065 Univ.~ AK IIA 533 494 329 415 716 663 442 559 9
## 4 11462 Univ.~ AK IIA 612 507 414 498 825 681 557 670 115
## 5 1002 Alaba~ AL IIA 442 369 310 350 530 444 376 423 59
## 6 1004 Unive~ AL IIA 441 385 310 388 542 473 383 477 57
## # ... with 4 more variables: V14 <dbl>, V15 <dbl>, V16 <dbl>, V17 <dbl>
?read.csv
## starting httpd help server ...
## done
dta <-read.csv("C:/tmp/ncku_roster.csv",sep=",", header = T, stringsAsFactors = FALSE)
dta1 <- dta[,-c(1,3:7)]
head(dta1)
## [1] " "
## [2] "心理系 3 "
## [3] "心理系 3 "
## [4] "心理系 4 "
## [5] "心理系 4 "
## [6] "教育所 1 碩 "
dta <- read.table("C:/tmp/P005.txt", header=T , stringsAsFactor=F, fill=T )
str(dta)
## 'data.frame': 49 obs. of 8 variables:
## $ City : chr "Atlanta" "Austin" "Bakersfield" "Baltimore" ...
## $ COL : chr "169" "143" "339" "173" ...
## $ PD : chr "414" "239" "43" "951" ...
## $ URate : num 13.6 11 23.7 21 255 NA 24.4 39.2 31.5 229 ...
## $ Pop : num 1790128 396891 349874 2147850 16 ...
## $ Taxes : num 5128 4303 4166 5001 411725 ...
## $ Income: int 2961 1711 2122 4654 3965 NA 5634 7213 5535 4839 ...
## $ RTWL : int 1 1 0 0 1620 NA 0 0 0 7224 ...
t.test(dta$Income, dta$Taxes)
##
## Welch Two Sample t-test
##
## data: dta$Income and dta$Taxes
## t = -1.956, df = 39.037, p-value = 0.05765
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1282681.91 21476.25
## sample estimates:
## mean of x mean of y
## 57561.03 688163.85
cor.test(dta$Income, dta$Taxes)
##
## Pearson's product-moment correlation
##
## data: dta$Income and dta$Taxes
## t = -0.34846, df = 36, p-value = 0.7295
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.3707901 0.2666463
## sample estimates:
## cor
## -0.05797939
jsp <- read.table("C:/tmp/juniorSchools.txt", header=T , stringsAsFactor=F)
jsp$Gender <- jsp$sex
##複製sex數列成gender
head(jsp)
## school class sex soc ravens pupil english math year Gender
## 1 S1 C1 G 9 23 P1 72 23 0 G
## 2 S1 C1 G 9 23 P1 80 24 1 G
## 3 S1 C1 G 9 23 P1 39 23 2 G
## 4 S1 C1 B 2 15 P2 7 14 0 B
## 5 S1 C1 B 2 15 P2 17 11 1 B
## 6 S1 C1 B 2 22 P3 88 36 0 B
jsp$soc <- factor(jsp$soc)
levels(jsp$soc) <- c("I", "II", "III_0man", "III_man", "IV", "V", "VI_Unemp_L", "VII_emp_NC", "VIII_Miss_Dad")
plot(jsp$soc, jsp$math, xlab = "SOC", ylab = "math")
##level階層化之下的社會變量構圖
saveRDS(jsp, file="C:/tmp/jsp.rda")